这是indexloc提供的服务,不要输入任何密码
Skip to content

Tags: huggingface/optimum-quanto

Tags

v0.2.7

Toggle v0.2.7's commit message
chore: release 0.2.7

v0.2.6

Toggle v0.2.6's commit message
chore: cut release branch and prepare 0.2.6

v0.2.5

Toggle v0.2.5's commit message
chore: release 0.2.5

v0.2.4

Toggle v0.2.4's commit message
release: 0.2.4

v0.2.3

Toggle v0.2.3's commit message
release: 0.2.3

v0.2.2

Toggle v0.2.2's commit message
chore: release 0.2.2

v0.2.1

Toggle v0.2.1's commit message
release: 0.2.1

v0.2.0

Toggle v0.2.0's commit message
release: 0.2.0

New:
- requantize helper by @calmitchell617,
- StableDiffusion example by @thliang01,
- improved linear backward path,
- AWQ int4 kernels.

v0.1.0

Toggle v0.1.0's commit message
release: 0.1.0

- group-wise quantization,
- safe serialization.

v0.0.13

Toggle v0.0.13's commit message
release: 0.0.13

- new `QConv2d` quantized module,
- official support for `float8` weights.

- fix `QbitsTensor.to()` that was not moving the inner tensors,
- prevent shallow `QTensor` copies when loading weights that do not move
  inner tensors.